message-bird

Warn

Audited by Snyk on Apr 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md instructs the agent to read and proxy data from the MessageBird API via Membrane (e.g., "List Messages", "Get Message" and the "Proxy requests" sections), which exposes user-generated/untrusted message and contact content that the agent is expected to interpret and can influence subsequent actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 11:19 PM
Issues
1